huggingface/swift-coreml-transformers

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1682 stars · 176 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Swift library with Core ML implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT, including tokenizers and demo apps for on-device text generation and question answering. The repository has been archived and is no longer maintained, with swift-transformers as its successor.

Use cases

• run GPT-2 text generation on an iPhone with Core ML
• implement BERT question answering on-device in Swift
• convert PyTorch transformer models to Core ML format
• use a WordPiece tokenizer in a Swift app
• build a demo app for on-device NLP inference

When to choose

• you need to run GPT-2 or BERT inference fully on-device in an Apple app
• you want reference Swift implementations of transformer tokenizers and decoding strategies
• you are targeting older Core ML 3 tooling or studying archived example code

When to avoid

• you need an actively maintained library - use huggingface/swift-transformers instead
• you need modern transformer architectures beyond GPT-2 and BERT
• you require server-side or GPU-cluster inference rather than on-device Core ML

Facets

library · maturity abandoned

machine-learning nlp llm-inference parser machine-learning apple-ecosystem deep-learning core-ml transformers gpt-2 bert on-device-inference text-generation question-answering archived natural-language-processing swift ios macos apple-ecosystem

Member repositories

For agents

markdown · JSON · MCP: product_card(name="huggingface/swift-coreml-transformers")